Electric vehicle operation safety rack detection and evaluation method and system

By aligning visual and bench data, extracting motion and component state features, and using autoencoders and spatiotemporal graph convolutional networks to generate a comprehensive safety index, the problem of insufficient joint analysis of visual perception technology and bench data in electric vehicle operation safety testing is solved, achieving efficient and reliable safety assessment and testing optimization.

CN122108628APending Publication Date: 2026-05-29CHERY INTELLIGENT VEHICLE TECH (HEFEI) CO LTD
1 Cites 0 Cited by

Patent Information

Application Number
CN202610020551.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-01-08
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

Existing methods for testing the operational safety of electric vehicles lack the combined analysis of visual perception technology and bench data, resulting in delayed fault identification and an inability to comprehensively and accurately assess the vehicle's safety status.

Method used

By aligning visual data and bench data, motion state features and component state features are extracted, and feature fusion is performed using autoencoder networks and spatiotemporal graph convolutional networks to generate a comprehensive safety index for safety assessment and determination.

Benefits of technology

It enables a comprehensive and dynamic assessment of the operational safety of electric vehicles, improves testing accuracy and stability, and allows for timely adjustment of testing conditions and optimization of testing procedures to ensure the operational safety of electric vehicles.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses an electric vehicle operation safety rack detection evaluation method and system, and belongs to the technical field of vehicle safety detection, and the evaluation method comprises the steps: carrying out the alignment processing of obtained original visual data and original rack data, carrying out the feature extraction, carrying out the fusion of features, and carrying out the safety evaluation processing, and obtaining a comprehensive safety index, and performing safety judgment processing according to the comprehensive safety index and a preset global threshold to obtain a judgment result. According to the method, the visual perception technology and the traditional rack data are fused, the accuracy of electric vehicle operation safety detection is improved, the safety states of the vehicle under different working conditions can be evaluated more comprehensively and accurately, the stability and adaptability of detection are enhanced through the space-time diagram convolutional network, and the detection accuracy is improved. The system can cope with complex and changeable test environments and vehicle running states, and provides an efficient and reliable solution for safety detection of the electric vehicle.
Need to check novelty before this filing date? Find Prior Art